Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2013
Analysis of adventitious lung sounds originating from pulmonary tuberculosis.
Tuberculosis is a common and potentially deadly infectious disease, usually affecting the respiratory system and causing the sound properties of symptomatic infected lungs to differ from non-infected lungs. Auscultation is often ruled out as a reliable diagnostic technique for TB due to the random distribution of the infection and the varying severity of damage to the lungs. However, advancements in signal processing techniques for respiratory sounds can improve the potential of auscultation far beyond the capabilities of the conventional mechanical stethoscope. ⋯ These features were then employed to train a neural network to automatically classify the auscultation recordings into their respective healthy or TB-origin categories. The neural network yielded a diagnostic accuracy of 73%, but it is believed that automated filtering of the noise in the clinics, more training samples and perhaps other signal processing methods can improve the results of future studies. This work demonstrates the potential of computer-aided auscultation as an aid for the diagnosis and treatment of TB.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2013
Multivariate temporal symptomatic characterization of cardiac arrest.
We model the temporal symptomatic characteristics of 171 cardiac arrest patients in Intensive Care Units. The temporal and feature dependencies in the data are illustrated using a mixture of matrix normal distributions. We found that the cardiac arrest temporal signature is best summarized with six hours data prior to cardiac arrest events, and its statistical descriptions are significantly different from the measurements taken in the past two days. This matrix normal model can classify these patterns better than logistic regressions with lagged features.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2013
Osteoporosis risk prediction using machine learning and conventional methods.
A number of clinical decision tools for osteoporosis risk assessment have been developed to select postmenopausal women for the measurement of bone mineral density. We developed and validated machine learning models with the aim of more accurately identifying the risk of osteoporosis in postmenopausal women, and compared with the ability of a conventional clinical decision tool, osteoporosis self-assessment tool (OST). We collected medical records from Korean postmenopausal women based on the Korea National Health and Nutrition Surveys (KNHANES V-1). ⋯ Validation on the test set showed that SVM predicted osteoporosis risk with an AUC of 0.827, accuracy of 76.7%, sensitivity of 77.8%, and specificity of 76.0%. We were the first to perform comparisons of the performance of osteoporosis prediction between the machine learning and conventional methods using population-based epidemiological data. The machine learning methods may be effective tools for identifying postmenopausal women at high risk for osteoporosis.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2013
Microwave technology for localization of traumatic intracranial bleedings-a numerical simulation study.
Traumatic brain injury (TBI) is a major public health problem worldwide. Intracranial bleedings represents the most serious complication of TBI and need to be surgically evacuated promptly to save lives and mitigate injury. ⋯ The classification accuracy is 94-100% for all classes, a result that encourages us to pursue our efforts with MWT for more realistic scenarios. This indicates that MWT has potential for localizing a detected bleeding, which would increase the diagnostic value of this technique.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2013
An algorithm to improve the estimation accuracy of a non-invasive method for cardiac output measurement based on prolonged expiration.
Cardiac output (CO) monitoring is important in the hemodynamic management of critically ill patients. In a previous study, a novel non-invasive technique for CO monitoring based on prolonged expiration was proposed. The novel method showed good agreement with thermodilution on stable mechanically ventilated patients; unstable patients were excluded. ⋯ This prospective study has been carried out on three cardiac surgery patients; eighteen CO measurements were performed on each patient, and these values were compared with data obtained by thermodilution. The designed and tested algorithm allowed to reach a good agreement between CO measured by our method and by thermodilution (e.g., the mean percentage differences were 4%, 11% and 3%). Even though further validation is necessary, the results are quite promising and the adopted solution appears to allow the suitability of the prolonged expiration method also on unstable patients.